Operations and AI analysis · Free to install
Small business operations system (Sales, Distribution and Inventory Management System) and an AI assistant run on your machine. Connect your subscribed language models or multi-model aggregators — not as an unsupervised single model, but as a structured pipeline: a team of workers you brief, with only the data you choose to send.
01 — Idea
The golivingbest family spans analysis and operations: glb_ai with glb_ai_web; and glb_ops, a sales, distribution and inventory management system, with glb_ops_client for operators and glb_ops_mobile for wholesale customers. The family is free to install and use without limitation. glb_ai and glb_ops are open source under the MIT License. glb_ai_web, glb_ops_client, and glb_ops_mobile are proprietary (source not open) but free to install.
glb_ai is an AI assistant you configure through the glb_ai_web console. It pulls data in through a SCREENER plugin, runs analysis in a structured pipeline (workers you brief, with an orchestrator that makes the final call), then pushes results out through a TRACKER plugin. The SCREENER can extract from any source you plug in — open APIs, databases, market feeds, legacy systems. The TRACKER can send results to any destination the same way. Models never touch your databases directly; only the plugin decides what leaves and what returns. Any developer is free to build a custom SCREENER or TRACKER by following the plugin development standard.
glb_ops is a sales, distribution and inventory management system for SMEs — not a complete ERP. It covers retail POS, wholesale distribution, and inventory. It has its own AI assistant for tasks such as visual recognition on purchase documents. That capability lives inside glb_ops.
Because they belong to the golivingbest family, we also ship a ready SCREENER plugin so glb_ai can optionally extract data from glb_ops into a workspace for analysis.
In glb_ai, models never open your databases. A SCREENER plugin is the controlled bridge — it extracts only the data slices you allow from whatever source you connect: APIs, databases, feeds, or other business systems.
Each workspace runs a linear job: GENERATOR drafts, REVIEWER checks, JUDGE settles conflict. Several workers form a pipeline. The orchestrator is the team leader who makes the last call.
Plugins are not one-way. A TRACKER takes the team’s verified response and dispatches it to the destination you choose — another system, a webhook, a report store, or an operational action endpoint.
02 — Models
The golivingbest family is free to install and use. glb_ai and glb_ops are open source (MIT). glb_ai_web, glb_ops_client, and glb_ops_mobile are proprietary but free to install.
Recommended
The one-touch evaluation pack: glb_ops API and demo database, glb_ai, and the glb_ai_web UI. You host the stack, connecting your chosen language models or model aggregator when a pipeline runs.
Use when you want operations and the analysis team running together on one machine.
Operations
A lightweight business operations backend for SMEs: point of sale, wholesale distribution, and inventory. It is a skeleton to build on — not a giant licence of which you will use half. Visual recognition speeds data entry; further AI assistants can be added on request. Interested in a fit for your entity? Ask about customisation.
Use when you need day-to-day sales, distribution, and inventory operations with glb_ops — without buying a heavy, oversized commercial software package.
Windows
The Windows desktop client for glb_ops: POS, wholesale, and stock work on the operator’s machine. It talks to the glb_ops API only — never to PostgreSQL, and never to an AI model directly.
Use when staff need a desktop console for daily operations.
Mobile
A client portal for wholesale customers to place sales orders from a desktop browser or mobile device. Operators fulfil those orders on the glb_ops backend. Customers follow each order through Preparing, Picking, Delivering, and Delivered, and can review their fulfilled order history. Like glb_ai_web, glb_ops_mobile is free to use with no licence fee; the source is not open.
Use when wholesale customers need self-service ordering and order-status visibility.
Analysis
The control layer between your data and the models. You decide what a SCREENER plugin may extract. You write the prompts. A workspace (a worker) runs GENERATOR → REVIEWER → JUDGE. A pipeline is a team of those workers; the orchestrator delivers the final judgement. SCREENER and TRACKER are source- and destination-agnostic: any system can feed data in, and any system can receive TRACKER output.
Use when you need analysis without giving a model unsupervised access to the database.
Web
The browser console for glb_ai: configure workspaces, run pipelines, and read the team’s verdicts. Operators brief the workers here; they do not open the database to the models.
Use when you want to run and inspect the analysis team in a browser.
03 — Install
We package the evaluation suite with Docker so Postgres, glb_ops, glb_ai, and the web UI start together on one machine — fewer host dependencies and a repeatable demo. If you want a non-Docker install with source for glb_ai and glb_ops, a compiled glb_ai_web binary, and the PostgreSQL demo database, contact us. After the API is running, install the Windows desktop client.
glb-suite-eval-1.0.0.zip.golivingbest-suite-eval-1.0.0, then run ./install.sh.:5022, AI API :8010, ops API :8000, Postgres :5433. Later edit .env in the suite folder you chose (same folder as the installer) to change LLM settings.golivingbest_ai_web to launch glb_ai_web. Sign in with the demo account — user PK0003, password demo.
# 1) Install Docker on your local PC or server
# - macOS: Docker Desktop
# - Linux: Docker Engine + Compose v2
# Start Docker, then check:
$ docker info
# 2) Prepare LLM_BASE_URL and LLM_API_KEY
# Needed for the AI assistant and golivingbest operations system.
# 3) Download the suite zip from this site (Downloads)
# Choose “Complete evaluation suite (Docker)”
# file: glb-suite-eval-1.0.0.zip
# Unzip into a folder where you want to run the suite
# (do not leave it only in Downloads)
$ mkdir -p ~/golivingbest
$ unzip glb-suite-eval-1.0.0.zip -d ~/golivingbest
$ cd ~/golivingbest/golivingbest-suite-eval-1.0.0
# 4) Run the installer
$ chmod +x install.sh
$ ./install.sh
# 5) Installer prompts (press Enter to accept defaults)
License: see LICENSE in this folder.
By continuing, you agree to those terms.
Press Enter to continue...
1. Database password for 'dgstar' [...]: dgstar
2. LLM_BASE_URL [...]: https://api.poe.com/v1
3. LLM_API_KEY (optional)...
4. LLM_MODEL_NAME [...]: gemini-3.1-flash-lite
# 6) Containers start — open when ready
glb_ops API: http://localhost:8000/docs
golivingbest AI: http://localhost:8010/docs
Web UI: http://localhost:5022/
Postgres DB: localhost:5433
# 7) Later: change LLM provider / key / model
# Edit .env in the suite folder where you unzipped:
# e.g. ~/golivingbest/golivingbest-suite-eval-1.0.0/.env
# (same folder as install.sh and docker-compose.yml)
$ cd ~/golivingbest/golivingbest-suite-eval-1.0.0
$ nano .env
# set LLM_API_KEY, LLM_BASE_URL, LLM_MODEL_NAME
$ docker compose up -dglb-suite-eval-1.0.0.zip.golivingbest-suite-eval-1.0.0, then run install.bat.:5022, AI API :8010, ops API :8000, Postgres :5433. Later edit .env in the suite folder you chose (same folder as the installer) to change LLM settings.golivingbest_ai_web to launch glb_ai_web. Sign in with the demo account — user PK0003, password demo.
REM 1) Install Docker on your local PC or server
REM - Windows / Windows Server: Docker Desktop (or Engine)
REM Start Docker Desktop, then check in Command Prompt or PowerShell:
C:\> docker info
REM 2) Prepare LLM_BASE_URL and LLM_API_KEY
REM Needed for the AI assistant and golivingbest operations system.
REM 3) Download the suite zip from this site (Downloads)
REM Choose “Complete evaluation suite (Docker)”
REM file: glb-suite-eval-1.0.0.zip
REM Unzip into a folder where you want to run the suite
REM (do not leave it only in Downloads)
REM Example destination: C:\golivingbest\golivingbest-suite-eval-1.0.0
REM Use File Explorer, 7-Zip, WinRAR, etc. to extract there.
C:\> cd C:\golivingbest\golivingbest-suite-eval-1.0.0
REM 4) Run the Windows installer
C:\golivingbest\golivingbest-suite-eval-1.0.0> install.bat
REM 5) Installer prompts (press Enter to accept defaults)
License: see LICENSE in this folder.
By continuing, you agree to those terms.
Press Enter to continue...
1. Database password for 'dgstar' [...]: dgstar
2. LLM_BASE_URL [...]: https://api.poe.com/v1
3. LLM_API_KEY (optional)...
4. LLM_MODEL_NAME [...]: gemini-3.1-flash-lite
REM 6) Containers start — open when ready
glb_ops API: http://localhost:8000/docs
golivingbest AI: http://localhost:8010/docs
Web UI: http://localhost:5022/
Postgres DB: localhost:5433
REM 7) Later: change LLM provider / key / model
REM Edit .env in the suite folder where you unzipped:
REM e.g. C:\golivingbest\golivingbest-suite-eval-1.0.0\.env
REM (same folder as install.bat and docker-compose.yml)
C:\> cd C:\golivingbest\golivingbest-suite-eval-1.0.0
C:\golivingbest\golivingbest-suite-eval-1.0.0> notepad .env
REM set LLM_API_KEY, LLM_BASE_URL, LLM_MODEL_NAME
C:\golivingbest\golivingbest-suite-eval-1.0.0> docker compose up -dgolivingbest_suite (Docker) so the ops API is available — usually http://localhost:8000/.glb_ops_client_installer.zip.glb_ops_client_installer, then run glb_ops_client_installer.exe.http://localhost:8000/ if Docker is on this PC, or enter another machine’s IP (e.g. http://192.168.1.69:8000/). Click Install.apiservices.apibaseurl if needed.DGStar.exe.glb_ops_client, start the Docker containers with Run as administrator. Then sign in with user PK0003 and password demo.
REM Prerequisite: glb_ops API already running (from golivingbest_suite above)
REM 1) Download glb_ops_client installer zip from this site (Downloads)
REM Choose “glb_ops Windows desktop client”
REM file: glb_ops_client_installer.zip
REM 2) Unzip to a folder where you want to keep the installer pack
REM (do not leave it only in Downloads)
REM Example: C:\glb_ops_client\
REM Use File Explorer, 7-Zip, WinRAR, etc.
C:\> cd C:\glb_ops_client\glb_ops_client_installer
REM 3) Run the installer (double-click in Explorer, or:)
C:\glb_ops_client\glb_ops_client_installer> glb_ops_client_installer.exe
REM 4) In the installer window:
REM - Choose the Destination folder for glb_ops_client
REM - Edit the glb_ops backend URL
REM Keep http://localhost:8000/ if Docker suite is on this PC
REM Or use the other machine’s IP, e.g. http://192.168.1.69:8000/
REM - Click Install
REM 5) Optional later: edit client settings (database + API)
REM In the installed Destination folder, open DGStarAppSettings.json
C:\Program Files\glb_ops_client> notepad DGStarAppSettings.json
REM Example DGStarAppSettings.json:
{
"DatabaseConnection": {
"DatabaseName": "dgstar_demo",
"Username": "dgstar",
"Password": "dgstar"
},
"apiservices": {
"apibaseurl": "http://localhost:8000/"
}
}
REM 6) Start the desktop client from the install Destination folder
C:\Program Files\glb_ops_client> DGStar.exeScan this QR code to open glb_ops_mobile. Download or print the image for a counter or warehouse sign. On the login page, sign in with the demo account — user PK0003, password demo — then use Install to add the app to your home screen.
Open https://order.golivingbest.com
https://order.golivingbest.com in Chrome.https://order.golivingbest.com in your favorite browser on iPhone. On the login page, sign in with the demo account — user PK0003, password demo.04 — Demos
Browse operation walkthroughs for glb_ops, glb_ops_mobile, and glb_ai. Open a row to step through screen snapshots — one image at a time.
05 — Downloads
Buttons will point at the suite zip and the WPF installer. Large files stay on the VPS.
06 — About us
AI is changing how software is built — with less time, lower cost, and fewer errors. We believe the era of the oversized software package is ending, and a new era of customized software is taking shape.
You should pay only for what you need — not a large licence when you use only a fraction of its features. With AI, tailored software can be built quickly and affordably. What developers bring is business knowledge and experience.
The golivingbest family was built with the help of AI, and it is designed to be shaped around your requirements. How far it can go for you is limited only by your imagination.
If you use the golivingbest family without customization or consultancy, it is completely free — and you may use it anywhere. We charge only for customization and on-demand consultancy — no licence fee, yearly or otherwise.
glb_ai and glb_ops are open source under the MIT License. glb_ai_web, glb_ops_client, and glb_ops_mobile are proprietary (source not open) but free to install. Language models are engaged as a structured team that you brief and direct — they never open the database themselves.
07 — Contact
Ask about glb_ops customisation, extra AI assistants, or production deployment. We will reply by email.